Can internlm3 8b instruct run on the Mac M1 Pro 32GB?
Yes. At 8K context the best fit is F16, using about 17.4 GB of the 21.4 GB usable on the Mac M1 Pro 32GB. Estimated speed ceiling: ~11 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|
| 2-bit (Q2_K) • | 4.0 GB Fits | 4.2 GB Fits | 5.4 GB Fits | 58 |
| 3-bit (Q3_K_M) • | 4.9 GB Fits | 5.1 GB Fits | 6.2 GB Fits | 46 |
| 4-bit (Q4_K_M) • | 5.8 GB Fits | 6.0 GB Fits | 7.1 GB Fits | 37 |
| 5-bit (Q5_K_M) • | 6.7 GB Fits | 6.9 GB Fits | 8.0 GB Fits | 32 |
| 6-bit (Q6_K) • | 7.6 GB Fits | 7.8 GB Fits | 8.9 GB Fits | 28 |
| 8-bit (Q8_0) • | 9.5 GB Fits | 9.7 GB Fits | 10.9 GB Fits | 21 |
| 16-bit (F16/BF16) | 17.2 GB Fits | 17.4 GB Fits | 18.5 GB Fits | 11 |
• real GGUF file size from internlm/internlm3-8b-instruct-gguf. Speed is a bandwidth ceiling (200 GB/s), not a benchmark. Methodology.
More
internlm3 8b instruct on every GPU and Mac · Every model that runs on the Mac M1 Pro 32GB · Apple Silicon guide · Try other settings in the calculator
Data: Hugging Face Hub (internlm/internlm3-8b-instruct), Apple specs. Data as of 2026-11-17.